RANDM: Random Access Depth Map Compression Using Range-Partitioning and Global Dictionary

Pratapa, Srihari; Manocha, Dinesh

doi:10.1145/3384382.3384524

Cited by 1 publication

(2 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the ability of the UNCC algorithm decoding blocks individually allows reconstruction of the depth map by sharing only the plane metadata between the frontend and the backend. It is noted that it takes an average of 1.24

s to decode a single block from the compressed depth image which is comparable to Pratapa et al [ 38 ] who present a random access compression technique on individual depth frames. This allows the possibility to further decrease the bandwidth of the computation load on both the frontend and the backend in future work.…”

Section: Experiments and Resultsmentioning

confidence: 68%

See 1 more Smart Citation

Low-Bandwidth and Compute-Bound RGB-D Planar Semantic SLAM

Zhang

Ganesh

Volle

et al. 2021

Sensors

View full text Add to dashboard Cite

Visual simultaneous location and mapping (SLAM) using RGB-D cameras has been a necessary capability for intelligent mobile robots. However, when using point-cloud map representations as most RGB-D SLAM systems do, limitations in onboard compute resources, and especially communication bandwidth can significantly limit the quantity of data processed and shared. This article proposes techniques that help address these challenges by mapping point clouds to parametric models in order to reduce computation and bandwidth load on agents. This contribution is coupled with a convolutional neural network (CNN) that extracts semantic information. Semantics provide guidance in object modeling which can reduce the geometric complexity of the environment. Pairing a parametric model with a semantic label allows agents to share the knowledge of the world with much less complexity, opening a door for multi-agent systems to perform complex tasking, and human–robot cooperation. This article takes the first step towards a generalized parametric model by limiting the geometric primitives to a planar surface and providing semantic labels when appropriate. Two novel compression algorithms for depth data and a method to independently fit planes to RGB-D data are provided, so that plane data can be used for real-time odometry estimation and mapping. Additionally, we extend maps with semantic information predicted from sparse geometries (planes) by a CNN. In experiments, the advantages of our approach in terms of computational and bandwidth resources savings are demonstrated and compared with other state-of-the-art SLAM systems.

show abstract

Section: Experiments and Resultsmentioning

confidence: 68%

“…Wildeboer et al [ 37 ] present an H.264 based scheme to compress depth maps from a video sequence. Pratapa et al [ 38 ] present a random-access depth compression algorithm that generates a compressed depth image by partitioning the scene into three parts and processing each part independently.…”

Section: Related Workmentioning

confidence: 99%